ABSTRACT
OBJECTIVES: To examine the comparative performance of EuroQol EQ-5D-5L and Center for Disease Control Healthy Days measures in assessing population health. METHODS: Using data from 2014 Alberta Community Health Survey, a cross-sectional population-based survey (N = 7559), conducted in Alberta, Canada, we examined construct validity of the measures as indicators of population health. Differences in EQ-5D-5L index score, visual analogue scale (EQ-VAS), and CDC unhealthy days index across socio-demographic subgroups were tested by Mann-Whitney and Kruskal-Wallis tests using known-groups approach. RESULTS: EQ-5D-5L and CDC Healthy Days provided comparable assessments of population health in this sample. Both measures discriminated between subgroups defined by self-perceived health status, level of education, and material deprivation. The discriminative ability of CDC Healthy Days was limited in capturing variability in health among age groups compared to the EQ-5D-5L. Among participants who reported 0 unhealthy days, the proportion of those with level 3 problems in pain/discomfort varied from 1.1% for participants aged 18-24 to 19.2% for those over 75 years. CONCLUSIONS: EQ-5D-5L demonstrated better construct validity than CDC Healthy Days in assessing health in a population-based sample of adults.
ABSTRACT
The paper introduces a multilayer long short-term memory (LSTM) based auto-encoder network to spot abnormalities in fetal ECG. The LSTM network was used to detect patterns in the time series, reconstruct errors and classify a given segment as an anomaly or not. The proposed anomaly detection method provides a filtering procedure able to reproduce ECG variability based on the semi-supervised paradigm. Experiments show that the proposed method can learn better features than the traditional approach without any prior knowledge and subject to proper signal identification can facilitate the analysis of fetal ECG signals in daily life.
